Source code for espnet.nets.pytorch_backend.transformer.multi_layer_conv

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

# Copyright 2019 Tomoki Hayashi
#  Apache 2.0  (http://www.apache.org/licenses/LICENSE-2.0)

import torch


[docs]class MultiLayeredConv1d(torch.nn.Module): """Multi-layered conv1d for Transformer block. This is a module of multi-leyered conv1d designed to replace positionwise feed-forward network in Transforner block, which is introduced in `FastSpeech: Fast, Robust and Controllable Text to Speech`_. Args: in_chans (int): Number of input channels. hidden_chans (int): Number of hidden channels. kernel_size (int): Kernel size of conv1d. dropout_rate (float): Dropout rate. .. _`FastSpeech: Fast, Robust and Controllable Text to Speech`: https://arxiv.org/pdf/1905.09263.pdf """ def __init__(self, in_chans, hidden_chans, kernel_size, dropout_rate): super(MultiLayeredConv1d, self).__init__() self.w_1 = torch.nn.Conv1d(in_chans, hidden_chans, kernel_size, stride=1, padding=(kernel_size - 1) // 2) self.w_2 = torch.nn.Conv1d(hidden_chans, in_chans, kernel_size, stride=1, padding=(kernel_size - 1) // 2) self.dropout = torch.nn.Dropout(dropout_rate)
[docs] def forward(self, x): """Calculate forward propagation. Args: x (Tensor): Batch of input tensors (B, *, in_chans). Returns: Tensor: Batch of output tensors (B, *, hidden_chans) """ x = torch.relu(self.w_1(x.transpose(-1, 1))).transpose(-1, 1) return self.w_2(self.dropout(x).transpose(-1, 1)).transpose(-1, 1)